Unconsolidated sandstone uranium deposits exploited by the in situ leaching (ISL) method, contain complex tetravalent and hexavalent uranium compounds, mostly as UO₂ and UO₃ oxides that have different dissolution rates in sulfuric acid solutions. This work investigates a reactive transport model that takes into account the dissolution of both UO₂ and UO₃ in sulfuric acid solution together with possible interactions with rock minerals during the ISL uranium extraction. Several empirical reaction rate constants were determined during lab experiments on uranium extraction assays, including dissolution rates of tetravalent and hexavalent uranium oxides, and the dissolution rate of rock components by sulfuric acid solution. Effects on the recovery of solution flow rates and ratios between tetravalent and hexavalent uranium compounds are also investigated. The experimental dissolution constants were then used in the proposed reactive transport model to be applied to a real case study in Kazakhstan for comparing the 16 months history matching of an exploitation block consisting of 18 well injectors and 4 producers. The obtained numerical results show good agreement with empirical data gathered during exploitation.

Roll-front uranium deposits are ore mineralizations that occur in sandstones or arkoses downstream from redox fronts or reduced/oxidized geochemical barriers. They are often bounded above and below by impermeable shaly/muddy layers making them ideal for in-situ leaching exploitation. Several stochastic simulations were previously investigated either to characterize the ore grade distribution within roll-front type deposits, or for describing geological processes involved in their formation. This work suggests some modifications/improvements of conventional geostatistical algorithms for honoring hydrodynamic constraints that govern fluid flows in ore bearing layers. In particular, instead of using the classical Euclidian or curvilinear (for Sgrid) distance for computing the variogram, it is proposed to calculate the variogram accounting for the time of flight (TOF) of water particles down the streamlines together with available well data. Non-deterministic streamline-based methods seem to provide more accurate interpolation results and resource estimation compared to a traditional geostatistical approach when applied to roll-front deposits.

The application of In Situ Leaching (ISL) has significantly boosted uranium production in countries like Kazakhstan. Given that hydrodynamic and chemical processes occur underground, mining enterprises worldwide have developed models of reactive transport. However, modeling these complex processes demands considerable computational resources. This issue is particularly significant in the context of numerical analyses of mining processes or when modeling production scenarios in uranium mining by the ISL technique, given that a substantial portion of computational resources is allocated to solving the hydraulic head equation. This work aims to explore the applicability of PINNs to accelerate hydrodynamic simulations of the ISL process. The solution of the Poisson equation is accelerated by generating an initial approximation for the iterative method through the application of the Inverse Distance Weighting (IDW) interpolation and PINNs. The impact of various factors, including the computational grid and the spacing between wells, on both the accuracy and efficiency of initial approximation and the overall solution of the elliptic equation are explored. Employing the hydraulic head distribution obtained through PINNs as the initial approximation led to a significant reduction in computation time and a decrease in the number of iterations by a factor of 2.8 to 7.10.

This study was conducted to assess the applicability of artificial neural networks (ANN) for forecasting the dynamics of uranium extraction over exploitation time during the process of In Situ Leaching (ISL). Currently, ISL process simulation involves multiple steps, starting with geostatistical interpolation, followed by computational fluid dynamics (CFD) and reactive transport simulation. While extensive research exists detailing each of these steps, machine learning techniques may offer the potential to directly obtain extraction curves (i.e., the concentration of the mineral produced over the exploitation time of the deposit), thereby bypassing these computationally expensive steps. As a basis, both an empirical experimental configuration and reactive transport simulations were used to generate training data for the neural network model. An ANN was constructed, trained, and tested on several test cases with different initial parameters, then the expected outcomes were compared to those derived from conventional modeling techniques. The results indicate that for the employed experimental configuration and a limited number of features, artificial intelligence technologies, specifically regression-based neural networks can model the recovery rate (or extraction degree) of the ISL process for mineral production, achieving a high degree of accuracy compared to traditional CFD and mass transport models.

The paper introduces a mathematical model that describes the cavitation process occurring during the passage of a water steam flow in various geometric configurations of a hydrodynamic device. The flow experiences a localized constriction (convergent nozzle) followed by expansion (divergent nozzle), exemplified by a Venturi tube or a Laval nozzle. A narrow flow channel connecting the convergent and divergent sections is equipped with a narrow-section nozzle for injecting methane molecules into the high-speed steam flow. As the steam-gas mixture passes through this zone, it is irradiated with an electron beam and sprayed into a cylindrical chamber at atmospheric pressure, where the distribution of methane molecules in water vapor forms an aerosol. Key geometric parameters of the constriction and expansion zones of the hydraulic system (cavitation-jet chamber) are determined to ensure the uniform distribution of dispersed-phase particles (methane) in the dispersion medium (water vapor). Velocity and pressure distributions of the mixed steam-gas flow are calculated using a turbulent mathematical model, specifically the k-ω model, while the motion of methane particles is simulated using a particle tracing method. The uniformity of methane molecule distribution in water vapor is assessed using Ripley’s K-function. The best performance of the hydrogen-producing chamber was observed when the cavitation-inducing nozzle’s convergence angle exceeded 50 degrees. The divergence angle of the nozzle within the range of 30–40 degrees provided the best distribution in terms of uniformity of the methane particles in the chamber.

In situ leaching represents an efficient and safe method for uranium mining, where a suboptimal well flow rate distribution leads to solution imbalances between wells, forming stagnant zones that increase operational costs. This study examines a real technological block from the Budenovskoye deposit, applying reactive transport modeling to optimize well flow rates and reduce operational time and reagent consumption. A reactive transport model was developed based on mass conservation and Darcy’s laws coupled with chemical kinetics describing sulfuric acid interactions with uranium minerals ($U{O}_2$ and $U{O}_3$). The model simulated a technological block with 4 production and 18 injection wells arranged in hexagonal cells over 511–542 days to achieve 90% uranium recovery. Six approaches for well flow rate redistribution were compared, based on different weighting factor calculation methods: advanced traditional, linear distance, squared distance, quadrilateral area, and two streamline-based approaches utilizing the minimum and average time of flight. The squared distance method achieved the highest efficiency, reducing operational costs by 5.7% through improved flow redistribution. The streamline-based methods performed comparably and offer potential advantages for heterogeneous conditions by automatically identifying hydraulic connections. The reactive transport modeling approach successfully demonstrated that multi-criteria optimization methods can improve ISL efficiency by 3.9%–5.7% while reducing operational costs.